Fixing empty accoubt id in locations

ExpediaGroup · Oct 2, 2023 · 6be5f19 · 6be5f19
1 parent 67e01f2
commit 6be5f19
Show file tree

Hide file tree

Showing 2 changed files with 21 additions and 13 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,10 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html). 
 
+## [3.0.15] - 2023-10-02
+### Fixed
+- Safeguard AWS account id call to prevent incorrect DB locations.
+
 ## [3.0.14] - 2023-08-11
 ### Changed
 - Upgrade Maven version from `3.9.3` to `3.9.4` as the older version no longer supported.(https://dlcdn.apache.org/maven/maven-3/)

diff --git a/files/startup.sh b/files/startup.sh
@@ -135,19 +135,23 @@ if [ -z $EXTERNAL_DATABASE ] && [ "$HIVE_METASTORE_ACCESS_MODE" = "readwrite" ];
         HIVE_APIARY_DB_NAMES="${HIVE_APIARY_DB_NAMES},${APIARY_SYSTEM_SCHEMA:-apiary_system}"
 
         AWS_ACCOUNT=`aws sts get-caller-identity|jq -r .Account`
-        for HIVE_DB in `echo ${HIVE_APIARY_DB_NAMES}|tr "," "\n"`
-        do
-            echo "creating hive database $HIVE_DB"
-            DB_ID=`echo "select MAX(DB_ID)+1 from DBS"|mysql $MYSQL_OPTIONS`
-            BUCKET_NAME=$(echo "${INSTANCE_NAME}-${AWS_ACCOUNT}-${AWS_REGION}-${HIVE_DB}"|tr "_" "-")
-            echo "insert into DBS(DB_ID,DB_LOCATION_URI,NAME,OWNER_NAME,OWNER_TYPE) values(\"$DB_ID\",\"s3://${BUCKET_NAME}/\",\"${HIVE_DB}\",\"root\",\"USER\") on duplicate key update DB_LOCATION_URI=\"s3://${BUCKET_NAME}/\";"|mysql $MYSQL_OPTIONS
-            #create glue database
-            if [ ! -z $ENABLE_GLUESYNC ]; then
-                echo "creating glue database $HIVE_DB"
-                aws --region=${AWS_REGION} glue create-database --database-input Name=${GLUE_PREFIX}${HIVE_DB},LocationUri=s3://${BUCKET_NAME}/ &> /dev/null
-                aws --region=${AWS_REGION} glue update-database --name=${GLUE_PREFIX}${HIVE_DB} --database-input "Name=${GLUE_PREFIX}${HIVE_DB},LocationUri=s3://${BUCKET_NAME}/,Description=Managed by ${INSTANCE_NAME} datalake."
-            fi
-        done
+        if [[ -n $AWS_ACCOUNT ]]; then
+          for HIVE_DB in `echo ${HIVE_APIARY_DB_NAMES}|tr "," "\n"`
+          do
+              echo "creating hive database $HIVE_DB"
+              DB_ID=`echo "select MAX(DB_ID)+1 from DBS"|mysql $MYSQL_OPTIONS`
+              BUCKET_NAME=$(echo "${INSTANCE_NAME}-${AWS_ACCOUNT}-${AWS_REGION}-${HIVE_DB}"|tr "_" "-")
+              echo "insert into DBS(DB_ID,DB_LOCATION_URI,NAME,OWNER_NAME,OWNER_TYPE) values(\"$DB_ID\",\"s3://${BUCKET_NAME}/\",\"${HIVE_DB}\",\"root\",\"USER\") on duplicate key update DB_LOCATION_URI=\"s3://${BUCKET_NAME}/\";"|mysql $MYSQL_OPTIONS
+              #create glue database
+              if [ ! -z $ENABLE_GLUESYNC ]; then
+                  echo "creating glue database $HIVE_DB"
+                  aws --region=${AWS_REGION} glue create-database --database-input Name=${GLUE_PREFIX}${HIVE_DB},LocationUri=s3://${BUCKET_NAME}/ &> /dev/null
+                  aws --region=${AWS_REGION} glue update-database --name=${GLUE_PREFIX}${HIVE_DB} --database-input "Name=${GLUE_PREFIX}${HIVE_DB},LocationUri=s3://${BUCKET_NAME}/,Description=Managed by ${INSTANCE_NAME} datalake."
+              fi
+          done
+        else
+          echo "Could not get AWS_ACCOUNT, skipping update of DB entries."
+        fi
     fi
 fi